基于机器视觉的骨架油封图像处理研究

Research on image processing of framework oil seal based on machine vision

为了实现对骨架油封内径尺寸的检测,判断油封质量,对基于机器视觉的骨架油封图像处理方法进行了研究。使用机器视觉系统实现了对图像的采集;使用MATLAB软件对骨架油封图像进行图像预处理、图像分割、边缘检测及尺寸特征提取等方面的研究;将检测出的骨架油封内径尺寸与标准尺寸对比,判断骨架油封是否合格。实验结果表明:经过图像预处理及阈值分割后的图像轮廓边缘清晰;Canny边缘检测算法检测出的边缘线连续且无过多伪线;设计的多角度直径检测法可以快速、有效的检测出内径尺寸变化,从而判断油封质量。

In order to detect the inner diameter of skeleton oil seal and judge the quality of oil seal,the image processing method of skeleton oil seal based on machine vision was studied.The image acquisition is realized by machine vision system.MATLAB software was used to study the image preprocessing,image segmentation,edge detection and dimension feature extraction of the skeleton oil seal image.The inner diameter of the detected oil seal is compared with the standard size to determine whether the oil seal of the skeleton is qualified.Experimental results show that the image edges are clear after image preprocessing and threshold segmentation.Canny edge detection algorithm detected continuous edge lines with few pseudo-lines.The designed multi-angle diameter detection method can quickly and effectively detect the change of inner diameter,so as to judge the quality of oil seal.